redirect to README

Changed link rendered invalid by Cease and Desist explained in new link. User is free to follow instructions back to HuggingFace to identify other instances of dataset but by only indirectly pointing to them, authors of model do not violate any potential Fair Use policy and risk having their model training data challenged.

Wishing you well.

README.md

@@ -133,7 +133,7 @@ The output mp4 file can be viewed by [VLC media player](https://www.videolan.org
 
 ## Training data
 
-The training data includes [LAION5B](https://huggingface.co/datasets/laion/laion2B-en), [ImageNet](https://www.image-net.org/), [Webvid](https://m-bain.github.io/webvid-dataset/) and other public datasets. Image and video filtering is performed after pre-training such as aesthetic score, watermark score, and deduplication.
+The training data includes [LAION5B](https://huggingface.co/datasets/laion/laion2B-en), [ImageNet](https://www.image-net.org/), [Webvid](https://github.com/m-bain/webvid/blob/main/README.md/) and other public datasets. Image and video filtering is performed after pre-training such as aesthetic score, watermark score, and deduplication.
 
 _(Part of this model card has been taken from [here](https://huggingface.co/damo-vilab/modelscope-damo-text-to-video-synthesis))_